10 files changed, 221 insertions, 144 deletions

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index b65a36defeb7..0c44196b78ac 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -74,31 +74,31 @@ extern void __bad_percpu_size(void);
 
 #define percpu_to_op(op, var, val)                      \
 do {                                                    \
-        typedef typeof(var) T__;                        \
+        typedef typeof(var) pto_T__;                    \
         if (0) {                                        \
-                T__ tmp__;                              \
-                tmp__ = (val);                          \
+                pto_T__ pto_tmp__;                      \
+                pto_tmp__ = (val);                      \
         }                                               \
         switch (sizeof(var)) {                          \
         case 1:                                         \
                 asm(op "b %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
-                    : "qi" ((T__)(val)));               \
+                    : "qi" ((pto_T__)(val)));           \
                 break;                                  \
         case 2:                                         \
                 asm(op "w %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
-                    : "ri" ((T__)(val)));               \
+                    : "ri" ((pto_T__)(val)));           \
                 break;                                  \
         case 4:                                         \
                 asm(op "l %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
-                    : "ri" ((T__)(val)));               \
+                    : "ri" ((pto_T__)(val)));           \
                 break;                                  \
         case 8:                                         \
                 asm(op "q %1,"__percpu_arg(0)           \
                     : "+m" (var)                        \
-                    : "re" ((T__)(val)));               \
+                    : "re" ((pto_T__)(val)));           \
                 break;                                  \
         default: __bad_percpu_size();                   \
         }                                               \
@@ -106,31 +106,31 @@ do {							\
 
 #define percpu_from_op(op, var, constraint)             \
 ({                                                      \
-        typeof(var) ret__;                              \
+        typeof(var) pfo_ret__;                          \
         switch (sizeof(var)) {                          \
         case 1:                                         \
                 asm(op "b "__percpu_arg(1)",%0"         \
-                    : "=q" (ret__)                      \
+                    : "=q" (pfo_ret__)                  \
                     : constraint);                      \
                 break;                                  \
         case 2:                                         \
                 asm(op "w "__percpu_arg(1)",%0"         \
-                    : "=r" (ret__)                      \
+                    : "=r" (pfo_ret__)                  \
                     : constraint);                      \
                 break;                                  \
         case 4:                                         \
                 asm(op "l "__percpu_arg(1)",%0"         \
-                    : "=r" (ret__)                      \
+                    : "=r" (pfo_ret__)                  \
                     : constraint);                      \
                 break;                                  \
         case 8:                                         \
                 asm(op "q "__percpu_arg(1)",%0"         \
-                    : "=r" (ret__)                      \
+                    : "=r" (pfo_ret__)                  \
                     : constraint);                      \
                 break;                                  \
         default: __bad_percpu_size();                   \
         }                                               \
-        ret__;                                          \
+        pfo_ret__;                                      \
 })
 
 /*
@@ -153,6 +153,84 @@ do {							\
 #define percpu_or(var, val)     percpu_to_op("or", per_cpu__##var, val)
 #define percpu_xor(var, val)    percpu_to_op("xor", per_cpu__##var, val)
 
+#define __this_cpu_read_1(pcp)          percpu_from_op("mov", (pcp), "m"(pcp))
+#define __this_cpu_read_2(pcp)          percpu_from_op("mov", (pcp), "m"(pcp))
+#define __this_cpu_read_4(pcp)          percpu_from_op("mov", (pcp), "m"(pcp))
+
+#define __this_cpu_write_1(pcp, val)    percpu_to_op("mov", (pcp), val)
+#define __this_cpu_write_2(pcp, val)    percpu_to_op("mov", (pcp), val)
+#define __this_cpu_write_4(pcp, val)    percpu_to_op("mov", (pcp), val)
+#define __this_cpu_add_1(pcp, val)      percpu_to_op("add", (pcp), val)
+#define __this_cpu_add_2(pcp, val)      percpu_to_op("add", (pcp), val)
+#define __this_cpu_add_4(pcp, val)      percpu_to_op("add", (pcp), val)
+#define __this_cpu_and_1(pcp, val)      percpu_to_op("and", (pcp), val)
+#define __this_cpu_and_2(pcp, val)      percpu_to_op("and", (pcp), val)
+#define __this_cpu_and_4(pcp, val)      percpu_to_op("and", (pcp), val)
+#define __this_cpu_or_1(pcp, val)       percpu_to_op("or", (pcp), val)
+#define __this_cpu_or_2(pcp, val)       percpu_to_op("or", (pcp), val)
+#define __this_cpu_or_4(pcp, val)       percpu_to_op("or", (pcp), val)
+#define __this_cpu_xor_1(pcp, val)      percpu_to_op("xor", (pcp), val)
+#define __this_cpu_xor_2(pcp, val)      percpu_to_op("xor", (pcp), val)
+#define __this_cpu_xor_4(pcp, val)      percpu_to_op("xor", (pcp), val)
+
+#define this_cpu_read_1(pcp)            percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_read_2(pcp)            percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_read_4(pcp)            percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_write_1(pcp, val)      percpu_to_op("mov", (pcp), val)
+#define this_cpu_write_2(pcp, val)      percpu_to_op("mov", (pcp), val)
+#define this_cpu_write_4(pcp, val)      percpu_to_op("mov", (pcp), val)
+#define this_cpu_add_1(pcp, val)        percpu_to_op("add", (pcp), val)
+#define this_cpu_add_2(pcp, val)        percpu_to_op("add", (pcp), val)
+#define this_cpu_add_4(pcp, val)        percpu_to_op("add", (pcp), val)
+#define this_cpu_and_1(pcp, val)        percpu_to_op("and", (pcp), val)
+#define this_cpu_and_2(pcp, val)        percpu_to_op("and", (pcp), val)
+#define this_cpu_and_4(pcp, val)        percpu_to_op("and", (pcp), val)
+#define this_cpu_or_1(pcp, val)         percpu_to_op("or", (pcp), val)
+#define this_cpu_or_2(pcp, val)         percpu_to_op("or", (pcp), val)
+#define this_cpu_or_4(pcp, val)         percpu_to_op("or", (pcp), val)
+#define this_cpu_xor_1(pcp, val)        percpu_to_op("xor", (pcp), val)
+#define this_cpu_xor_2(pcp, val)        percpu_to_op("xor", (pcp), val)
+#define this_cpu_xor_4(pcp, val)        percpu_to_op("xor", (pcp), val)
+
+#define irqsafe_cpu_add_1(pcp, val)     percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_add_2(pcp, val)     percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_add_4(pcp, val)     percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_and_1(pcp, val)     percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_and_2(pcp, val)     percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_and_4(pcp, val)     percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_or_1(pcp, val)      percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_or_2(pcp, val)      percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_or_4(pcp, val)      percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_xor_1(pcp, val)     percpu_to_op("xor", (pcp), val)
+#define irqsafe_cpu_xor_2(pcp, val)     percpu_to_op("xor", (pcp), val)
+#define irqsafe_cpu_xor_4(pcp, val)     percpu_to_op("xor", (pcp), val)
+
+/*
+ * Per cpu atomic 64 bit operations are only available under 64 bit.
+ * 32 bit must fall back to generic operations.
+ */
+#ifdef CONFIG_X86_64
+#define __this_cpu_read_8(pcp)          percpu_from_op("mov", (pcp), "m"(pcp))
+#define __this_cpu_write_8(pcp, val)    percpu_to_op("mov", (pcp), val)
+#define __this_cpu_add_8(pcp, val)      percpu_to_op("add", (pcp), val)
+#define __this_cpu_and_8(pcp, val)      percpu_to_op("and", (pcp), val)
+#define __this_cpu_or_8(pcp, val)       percpu_to_op("or", (pcp), val)
+#define __this_cpu_xor_8(pcp, val)      percpu_to_op("xor", (pcp), val)
+
+#define this_cpu_read_8(pcp)            percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_write_8(pcp, val)      percpu_to_op("mov", (pcp), val)
+#define this_cpu_add_8(pcp, val)        percpu_to_op("add", (pcp), val)
+#define this_cpu_and_8(pcp, val)        percpu_to_op("and", (pcp), val)
+#define this_cpu_or_8(pcp, val)         percpu_to_op("or", (pcp), val)
+#define this_cpu_xor_8(pcp, val)        percpu_to_op("xor", (pcp), val)
+
+#define irqsafe_cpu_add_8(pcp, val)     percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_and_8(pcp, val)     percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_or_8(pcp, val)      percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_xor_8(pcp, val)     percpu_to_op("xor", (pcp), val)
+
+#endif
+
 /* This is not atomic against other CPUs -- CPU preemption needs to be off */
 #define x86_test_and_clear_bit_percpu(bit, var)                         \
 ({                                                                      \
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index 6389432a9dbf..0159a69396cb 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -361,7 +361,7 @@ void stop_apic_nmi_watchdog(void *unused)
  */
 
 static DEFINE_PER_CPU(unsigned, last_irq_sum);
-static DEFINE_PER_CPU(local_t, alert_counter);
+static DEFINE_PER_CPU(long, alert_counter);
 static DEFINE_PER_CPU(int, nmi_touch);
 
 void touch_nmi_watchdog(void)
@@ -438,8 +438,8 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
                  * Ayiee, looks like this CPU is stuck ...
                  * wait a few IRQs (5 seconds) before doing the oops ...
                  */
-                local_inc(&__get_cpu_var(alert_counter));
-                if (local_read(&__get_cpu_var(alert_counter)) == 5 * nmi_hz)
+                __this_cpu_inc(per_cpu_var(alert_counter));
+                if (__this_cpu_read(per_cpu_var(alert_counter)) == 5 * nmi_hz)
                         /*
                          * die_nmi will return ONLY if NOTIFY_STOP happens..
                          */
@@ -447,7 +447,7 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
                                 regs, panic_on_timeout);
         } else {
                 __get_cpu_var(last_irq_sum) = sum;
-                local_set(&__get_cpu_var(alert_counter), 0);
+                __this_cpu_write(per_cpu_var(alert_counter), 0);
         }
 
         /* see if the nmi watchdog went off */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c1afa990a6c8..20399b7b0c3f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1093,7 +1093,7 @@ static void clear_all_debug_regs(void)
 
 void __cpuinit cpu_init(void)
 {
-        struct orig_ist *orig_ist;
+        struct orig_ist *oist;
         struct task_struct *me;
         struct tss_struct *t;
         unsigned long v;
@@ -1102,7 +1102,7 @@ void __cpuinit cpu_init(void)
 
         cpu = stack_smp_processor_id();
         t = &per_cpu(init_tss, cpu);
-        orig_ist = &per_cpu(orig_ist, cpu);
+        oist = &per_cpu(orig_ist, cpu);
 
 #ifdef CONFIG_NUMA
         if (cpu != 0 && percpu_read(node_number) == 0 &&
@@ -1143,12 +1143,12 @@ void __cpuinit cpu_init(void)
         /*
          * set up and load the per-CPU TSS
          */
-        if (!orig_ist->ist[0]) {
+        if (!oist->ist[0]) {
                 char *estacks = per_cpu(exception_stacks, cpu);
 
                 for (v = 0; v < N_EXCEPTION_STACKS; v++) {
                         estacks += exception_stack_sizes[v];
-                        orig_ist->ist[v] = t->x86_tss.ist[v] =
+                        oist->ist[v] = t->x86_tss.ist[v] =
                                         (unsigned long)estacks;
                 }
         }
diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c
index dca325c03999..b368cd862997 100644
--- a/arch/x86/kernel/cpu/cpu_debug.c
+++ b/arch/x86/kernel/cpu/cpu_debug.c
@@ -30,9 +30,9 @@
 #include <asm/apic.h>
 #include <asm/desc.h>
 
-static DEFINE_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpu_arr);
-static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], priv_arr);
-static DEFINE_PER_CPU(int, cpu_priv_count);
+static DEFINE_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpud_arr);
+static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], cpud_priv_arr);
+static DEFINE_PER_CPU(int, cpud_priv_count);
 
 static DEFINE_MUTEX(cpu_debug_lock);
 
@@ -531,7 +531,7 @@ static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg,
 
         /* Already intialized */
         if (file == CPU_INDEX_BIT)
-                if (per_cpu(cpu_arr[type].init, cpu))
+                if (per_cpu(cpud_arr[type].init, cpu))
                         return 0;
 
         priv = kzalloc(sizeof(*priv), GFP_KERNEL);
@@ -543,8 +543,8 @@ static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg,
         priv->reg = reg;
         priv->file = file;
         mutex_lock(&cpu_debug_lock);
-        per_cpu(priv_arr[type], cpu) = priv;
-        per_cpu(cpu_priv_count, cpu)++;
+        per_cpu(cpud_priv_arr[type], cpu) = priv;
+        per_cpu(cpud_priv_count, cpu)++;
         mutex_unlock(&cpu_debug_lock);
 
         if (file)
@@ -552,10 +552,10 @@ static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg,
                                     dentry, (void *)priv, &cpu_fops);
         else {
                 debugfs_create_file(cpu_base[type].name, S_IRUGO,
-                                    per_cpu(cpu_arr[type].dentry, cpu),
+                                    per_cpu(cpud_arr[type].dentry, cpu),
                                     (void *)priv, &cpu_fops);
                 mutex_lock(&cpu_debug_lock);
-                per_cpu(cpu_arr[type].init, cpu) = 1;
+                per_cpu(cpud_arr[type].init, cpu) = 1;
                 mutex_unlock(&cpu_debug_lock);
         }
 
@@ -615,7 +615,7 @@ static int cpu_init_allreg(unsigned cpu, struct dentry *dentry)
                 if (!is_typeflag_valid(cpu, cpu_base[type].flag))
                         continue;
                 cpu_dentry = debugfs_create_dir(cpu_base[type].name, dentry);
-                per_cpu(cpu_arr[type].dentry, cpu) = cpu_dentry;
+                per_cpu(cpud_arr[type].dentry, cpu) = cpu_dentry;
 
                 if (type < CPU_TSS_BIT)
                         err = cpu_init_msr(cpu, type, cpu_dentry);
@@ -647,11 +647,11 @@ static int cpu_init_cpu(void)
                 err = cpu_init_allreg(cpu, cpu_dentry);
 
                 pr_info("cpu%d(%d) debug files %d\n",
-                        cpu, nr_cpu_ids, per_cpu(cpu_priv_count, cpu));
-                if (per_cpu(cpu_priv_count, cpu) > MAX_CPU_FILES) {
+                        cpu, nr_cpu_ids, per_cpu(cpud_priv_count, cpu));
+                if (per_cpu(cpud_priv_count, cpu) > MAX_CPU_FILES) {
                         pr_err("Register files count %d exceeds limit %d\n",
-                                per_cpu(cpu_priv_count, cpu), MAX_CPU_FILES);
-                        per_cpu(cpu_priv_count, cpu) = MAX_CPU_FILES;
+                                per_cpu(cpud_priv_count, cpu), MAX_CPU_FILES);
+                        per_cpu(cpud_priv_count, cpu) = MAX_CPU_FILES;
                         err = -ENFILE;
                 }
                 if (err)
@@ -676,8 +676,8 @@ static void __exit cpu_debug_exit(void)
                 debugfs_remove_recursive(cpu_debugfs_dir);
 
         for (cpu = 0; cpu <  nr_cpu_ids; cpu++)
-                for (i = 0; i < per_cpu(cpu_priv_count, cpu); i++)
-                        kfree(per_cpu(priv_arr[i], cpu));
+                for (i = 0; i < per_cpu(cpud_priv_count, cpu); i++)
+                        kfree(per_cpu(cpud_priv_arr[i], cpu));
 }
 
 module_init(cpu_debug_init);
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index d2e7c77c1ea4..f28decf8dde3 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -68,9 +68,9 @@ struct acpi_cpufreq_data {
         unsigned int cpu_feature;
 };
 
-static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
+static DEFINE_PER_CPU(struct acpi_cpufreq_data *, acfreq_data);
 
-static DEFINE_PER_CPU(struct aperfmperf, old_perf);
+static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf);
 
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance *acpi_perf_data;
@@ -214,14 +214,14 @@ static u32 get_cur_val(const struct cpumask *mask)
         if (unlikely(cpumask_empty(mask)))
                 return 0;
 
-        switch (per_cpu(drv_data, cpumask_first(mask))->cpu_feature) {
+        switch (per_cpu(acfreq_data, cpumask_first(mask))->cpu_feature) {
         case SYSTEM_INTEL_MSR_CAPABLE:
                 cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
                 cmd.addr.msr.reg = MSR_IA32_PERF_STATUS;
                 break;
         case SYSTEM_IO_CAPABLE:
                 cmd.type = SYSTEM_IO_CAPABLE;
-                perf = per_cpu(drv_data, cpumask_first(mask))->acpi_data;
+                perf = per_cpu(acfreq_data, cpumask_first(mask))->acpi_data;
                 cmd.addr.io.port = perf->control_register.address;
                 cmd.addr.io.bit_width = perf->control_register.bit_width;
                 break;
@@ -268,8 +268,8 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy,
         if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1))
                 return 0;
 
-        ratio = calc_aperfmperf_ratio(&per_cpu(old_perf, cpu), &perf);
-        per_cpu(old_perf, cpu) = perf;
+        ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf);
+        per_cpu(acfreq_old_perf, cpu) = perf;
 
         retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT;
 
@@ -278,7 +278,7 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy,
 
 static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 {
-        struct acpi_cpufreq_data *data = per_cpu(drv_data, cpu);
+        struct acpi_cpufreq_data *data = per_cpu(acfreq_data, cpu);
         unsigned int freq;
         unsigned int cached_freq;
 
@@ -322,7 +322,7 @@ static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
 static int acpi_cpufreq_target(struct cpufreq_policy *policy,
                                unsigned int target_freq, unsigned int relation)
 {
-        struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+        struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
         struct acpi_processor_performance *perf;
         struct cpufreq_freqs freqs;
         struct drv_cmd cmd;
@@ -416,7 +416,7 @@ out:
 
 static int acpi_cpufreq_verify(struct cpufreq_policy *policy)
 {
-        struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+        struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
 
         dprintk("acpi_cpufreq_verify\n");
 
@@ -574,7 +574,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
                 return -ENOMEM;
 
         data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu);
-        per_cpu(drv_data, cpu) = data;
+        per_cpu(acfreq_data, cpu) = data;
 
         if (cpu_has(c, X86_FEATURE_CONSTANT_TSC))
                 acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS;
@@ -725,20 +725,20 @@ err_unreg:
         acpi_processor_unregister_performance(perf, cpu);
 err_free:
         kfree(data);
-        per_cpu(drv_data, cpu) = NULL;
+        per_cpu(acfreq_data, cpu) = NULL;
 
         return result;
 }
 
 static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
-        struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+        struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
 
         dprintk("acpi_cpufreq_cpu_exit\n");
 
         if (data) {
                 cpufreq_frequency_table_put_attr(policy->cpu);
-                per_cpu(drv_data, policy->cpu) = NULL;
+                per_cpu(acfreq_data, policy->cpu) = NULL;
                 acpi_processor_unregister_performance(data->acpi_data,
                                                       policy->cpu);
                 kfree(data);
@@ -749,7 +749,7 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 
 static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
 {
-        struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+        struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
 
         dprintk("acpi_cpufreq_resume\n");
 
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 6c40f6b5b340..0c06bca2a1dc 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -499,8 +499,8 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
 #ifdef CONFIG_SYSFS
 
 /* pointer to _cpuid4_info array (for each cache leaf) */
-static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info);
-#define CPUID4_INFO_IDX(x, y)   (&((per_cpu(cpuid4_info, x))[y]))
+static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info);
+#define CPUID4_INFO_IDX(x, y)   (&((per_cpu(ici_cpuid4_info, x))[y]))
 
 #ifdef CONFIG_SMP
 static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
@@ -513,7 +513,7 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
         if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
                 struct cpuinfo_x86 *d;
                 for_each_online_cpu(i) {
-                        if (!per_cpu(cpuid4_info, i))
+                        if (!per_cpu(ici_cpuid4_info, i))
                                 continue;
                         d = &cpu_data(i);
                         this_leaf = CPUID4_INFO_IDX(i, index);
@@ -535,7 +535,7 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
                             c->apicid >> index_msb) {
                                 cpumask_set_cpu(i,
                                         to_cpumask(this_leaf->shared_cpu_map));
-                                if (i != cpu && per_cpu(cpuid4_info, i))  {
+                                if (i != cpu && per_cpu(ici_cpuid4_info, i))  {
                                         sibling_leaf =
                                                 CPUID4_INFO_IDX(i, index);
                                         cpumask_set_cpu(cpu, to_cpumask(
@@ -574,8 +574,8 @@ static void __cpuinit free_cache_attributes(unsigned int cpu)
         for (i = 0; i < num_cache_leaves; i++)
                 cache_remove_shared_cpu_map(cpu, i);
 
-        kfree(per_cpu(cpuid4_info, cpu));
-        per_cpu(cpuid4_info, cpu) = NULL;
+        kfree(per_cpu(ici_cpuid4_info, cpu));
+        per_cpu(ici_cpuid4_info, cpu) = NULL;
 }
 
 static int
@@ -614,15 +614,15 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
         if (num_cache_leaves == 0)
                 return -ENOENT;
 
-        per_cpu(cpuid4_info, cpu) = kzalloc(
+        per_cpu(ici_cpuid4_info, cpu) = kzalloc(
             sizeof(struct _cpuid4_info) * num_cache_leaves, GFP_KERNEL);
-        if (per_cpu(cpuid4_info, cpu) == NULL)
+        if (per_cpu(ici_cpuid4_info, cpu) == NULL)
                 return -ENOMEM;
 
         smp_call_function_single(cpu, get_cpu_leaves, &retval, true);
         if (retval) {
-                kfree(per_cpu(cpuid4_info, cpu));
-                per_cpu(cpuid4_info, cpu) = NULL;
+                kfree(per_cpu(ici_cpuid4_info, cpu));
+                per_cpu(ici_cpuid4_info, cpu) = NULL;
         }
 
         return retval;
@@ -634,7 +634,7 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
 extern struct sysdev_class cpu_sysdev_class; /* from drivers/base/cpu.c */
 
 /* pointer to kobject for cpuX/cache */
-static DEFINE_PER_CPU(struct kobject *, cache_kobject);
+static DEFINE_PER_CPU(struct kobject *, ici_cache_kobject);
 
 struct _index_kobject {
         struct kobject kobj;
@@ -643,8 +643,8 @@ struct _index_kobject {
 };
 
 /* pointer to array of kobjects for cpuX/cache/indexY */
-static DEFINE_PER_CPU(struct _index_kobject *, index_kobject);
-#define INDEX_KOBJECT_PTR(x, y)         (&((per_cpu(index_kobject, x))[y]))
+static DEFINE_PER_CPU(struct _index_kobject *, ici_index_kobject);
+#define INDEX_KOBJECT_PTR(x, y)         (&((per_cpu(ici_index_kobject, x))[y]))
 
 #define show_one_plus(file_name, object, val)                           \
 static ssize_t show_##file_name                                         \
@@ -863,10 +863,10 @@ static struct kobj_type ktype_percpu_entry = {
 
 static void __cpuinit cpuid4_cache_sysfs_exit(unsigned int cpu)
 {
-        kfree(per_cpu(cache_kobject, cpu));
-        kfree(per_cpu(index_kobject, cpu));
-        per_cpu(cache_kobject, cpu) = NULL;
-        per_cpu(index_kobject, cpu) = NULL;
+        kfree(per_cpu(ici_cache_kobject, cpu));
+        kfree(per_cpu(ici_index_kobject, cpu));
+        per_cpu(ici_cache_kobject, cpu) = NULL;
+        per_cpu(ici_index_kobject, cpu) = NULL;
         free_cache_attributes(cpu);
 }
 
@@ -882,14 +882,14 @@ static int __cpuinit cpuid4_cache_sysfs_init(unsigned int cpu)
                 return err;
 
         /* Allocate all required memory */
-        per_cpu(cache_kobject, cpu) =
+        per_cpu(ici_cache_kobject, cpu) =
                 kzalloc(sizeof(struct kobject), GFP_KERNEL);
-        if (unlikely(per_cpu(cache_kobject, cpu) == NULL))
+        if (unlikely(per_cpu(ici_cache_kobject, cpu) == NULL))
                 goto err_out;
 
-        per_cpu(index_kobject, cpu) = kzalloc(
+        per_cpu(ici_index_kobject, cpu) = kzalloc(
             sizeof(struct _index_kobject) * num_cache_leaves, GFP_KERNEL);
-        if (unlikely(per_cpu(index_kobject, cpu) == NULL))
+        if (unlikely(per_cpu(ici_index_kobject, cpu) == NULL))
                 goto err_out;
 
         return 0;
@@ -913,7 +913,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
         if (unlikely(retval < 0))
                 return retval;
 
-        retval = kobject_init_and_add(per_cpu(cache_kobject, cpu),
+        retval = kobject_init_and_add(per_cpu(ici_cache_kobject, cpu),
                                       &ktype_percpu_entry,
                                       &sys_dev->kobj, "%s", "cache");
         if (retval < 0) {
@@ -927,12 +927,12 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
                 this_object->index = i;
                 retval = kobject_init_and_add(&(this_object->kobj),
                                               &ktype_cache,
-                                              per_cpu(cache_kobject, cpu),
+                                              per_cpu(ici_cache_kobject, cpu),
                                               "index%1lu", i);
                 if (unlikely(retval)) {
                         for (j = 0; j < i; j++)
                                 kobject_put(&(INDEX_KOBJECT_PTR(cpu, j)->kobj));
-                        kobject_put(per_cpu(cache_kobject, cpu));
+                        kobject_put(per_cpu(ici_cache_kobject, cpu));
                         cpuid4_cache_sysfs_exit(cpu);
                         return retval;
                 }
@@ -940,7 +940,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
         }
         cpumask_set_cpu(cpu, to_cpumask(cache_dev_map));
 
-        kobject_uevent(per_cpu(cache_kobject, cpu), KOBJ_ADD);
+        kobject_uevent(per_cpu(ici_cache_kobject, cpu), KOBJ_ADD);
         return 0;
 }
 
@@ -949,7 +949,7 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev)
         unsigned int cpu = sys_dev->id;
         unsigned long i;
 
-        if (per_cpu(cpuid4_info, cpu) == NULL)
+        if (per_cpu(ici_cpuid4_info, cpu) == NULL)
                 return;
         if (!cpumask_test_cpu(cpu, to_cpumask(cache_dev_map)))
                 return;
@@ -957,7 +957,7 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev)
 
         for (i = 0; i < num_cache_leaves; i++)
                 kobject_put(&(INDEX_KOBJECT_PTR(cpu, i)->kobj));
-        kobject_put(per_cpu(cache_kobject, cpu));
+        kobject_put(per_cpu(ici_cache_kobject, cpu));
         cpuid4_cache_sysfs_exit(cpu);
 }
 
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index ef42a038f1a6..1c47390dd0e5 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -265,13 +265,13 @@ struct ds_context {
         int                     cpu;
 };
 
-static DEFINE_PER_CPU(struct ds_context *, cpu_context);
+static DEFINE_PER_CPU(struct ds_context *, cpu_ds_context);
 
 
 static struct ds_context *ds_get_context(struct task_struct *task, int cpu)
 {
         struct ds_context **p_context =
-                (task ? &task->thread.ds_ctx : &per_cpu(cpu_context, cpu));
+                (task ? &task->thread.ds_ctx : &per_cpu(cpu_ds_context, cpu));
         struct ds_context *context = NULL;
         struct ds_context *new_context = NULL;
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 3de0b37ec038..1d9b33843c80 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -316,7 +316,7 @@ static void svm_hardware_disable(void *garbage)
 static int svm_hardware_enable(void *garbage)
 {
 
-        struct svm_cpu_data *svm_data;
+        struct svm_cpu_data *sd;
         uint64_t efer;
         struct descriptor_table gdt_descr;
         struct desc_struct *gdt;
@@ -331,63 +331,61 @@ static int svm_hardware_enable(void *garbage)
                        me);
                 return -EINVAL;
         }
-        svm_data = per_cpu(svm_data, me);
+        sd = per_cpu(svm_data, me);
 
-        if (!svm_data) {
+        if (!sd) {
                 printk(KERN_ERR "svm_hardware_enable: svm_data is NULL on %d\n",
                        me);
                 return -EINVAL;
         }
 
-        svm_data->asid_generation = 1;
-        svm_data->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
-        svm_data->next_asid = svm_data->max_asid + 1;
+        sd->asid_generation = 1;
+        sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
+        sd->next_asid = sd->max_asid + 1;
 
         kvm_get_gdt(&gdt_descr);
         gdt = (struct desc_struct *)gdt_descr.base;
-        svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
+        sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
 
         wrmsrl(MSR_EFER, efer | EFER_SVME);
 
-        wrmsrl(MSR_VM_HSAVE_PA,
-               page_to_pfn(svm_data->save_area) << PAGE_SHIFT);
+        wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT);
 
         return 0;
 }
 
 static void svm_cpu_uninit(int cpu)
 {
-        struct svm_cpu_data *svm_data
-                = per_cpu(svm_data, raw_smp_processor_id());
+        struct svm_cpu_data *sd = per_cpu(svm_data, raw_smp_processor_id());
 
-        if (!svm_data)
+        if (!sd)
                 return;
 
         per_cpu(svm_data, raw_smp_processor_id()) = NULL;
-        __free_page(svm_data->save_area);
-        kfree(svm_data);
+        __free_page(sd->save_area);
+        kfree(sd);
 }
 
 static int svm_cpu_init(int cpu)
 {
-        struct svm_cpu_data *svm_data;
+        struct svm_cpu_data *sd;
         int r;
 
-        svm_data = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
-        if (!svm_data)
+        sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
+        if (!sd)
                 return -ENOMEM;
-        svm_data->cpu = cpu;
-        svm_data->save_area = alloc_page(GFP_KERNEL);
+        sd->cpu = cpu;
+        sd->save_area = alloc_page(GFP_KERNEL);
         r = -ENOMEM;
-        if (!svm_data->save_area)
+        if (!sd->save_area)
                 goto err_1;
 
-        per_cpu(svm_data, cpu) = svm_data;
+        per_cpu(svm_data, cpu) = sd;
 
         return 0;
 
 err_1:
-        kfree(svm_data);
+        kfree(sd);
         return r;
 
 }
@@ -1092,16 +1090,16 @@ static void save_host_msrs(struct kvm_vcpu *vcpu)
 #endif
 }
 
-static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data)
+static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
 {
-        if (svm_data->next_asid > svm_data->max_asid) {
-                ++svm_data->asid_generation;
-                svm_data->next_asid = 1;
+        if (sd->next_asid > sd->max_asid) {
+                ++sd->asid_generation;
+                sd->next_asid = 1;
                 svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID;
         }
 
-        svm->asid_generation = svm_data->asid_generation;
-        svm->vmcb->control.asid = svm_data->next_asid++;
+        svm->asid_generation = sd->asid_generation;
+        svm->vmcb->control.asid = sd->next_asid++;
 }
 
 static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr)
@@ -2429,8 +2427,8 @@ static void reload_tss(struct kvm_vcpu *vcpu)
 {
         int cpu = raw_smp_processor_id();
 
-        struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu);
-        svm_data->tss_desc->type = 9; /* available 32/64-bit TSS */
+        struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+        sd->tss_desc->type = 9; /* available 32/64-bit TSS */
         load_TR_desc();
 }
 
@@ -2438,12 +2436,12 @@ static void pre_svm_run(struct vcpu_svm *svm)
 {
         int cpu = raw_smp_processor_id();
 
-        struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu);
+        struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 
         svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
         /* FIXME: handle wraparound of asid_generation */
-        if (svm->asid_generation != svm_data->asid_generation)
-                new_asid(svm, svm_data);
+        if (svm->asid_generation != sd->asid_generation)
+                new_asid(svm, sd);
 }
 
 static void svm_inject_nmi(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 64757c0ba5fc..563d20504988 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -35,10 +35,10 @@
 
 cpumask_var_t xen_cpu_initialized_map;
 
-static DEFINE_PER_CPU(int, resched_irq);
-static DEFINE_PER_CPU(int, callfunc_irq);
-static DEFINE_PER_CPU(int, callfuncsingle_irq);
-static DEFINE_PER_CPU(int, debug_irq) = -1;
+static DEFINE_PER_CPU(int, xen_resched_irq);
+static DEFINE_PER_CPU(int, xen_callfunc_irq);
+static DEFINE_PER_CPU(int, xen_callfuncsingle_irq);
+static DEFINE_PER_CPU(int, xen_debug_irq) = -1;
 
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
 static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
@@ -103,7 +103,7 @@ static int xen_smp_intr_init(unsigned int cpu)
                                     NULL);
         if (rc < 0)
                 goto fail;
-        per_cpu(resched_irq, cpu) = rc;
+        per_cpu(xen_resched_irq, cpu) = rc;
 
         callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu);
         rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
@@ -114,7 +114,7 @@ static int xen_smp_intr_init(unsigned int cpu)
                                     NULL);
         if (rc < 0)
                 goto fail;
-        per_cpu(callfunc_irq, cpu) = rc;
+        per_cpu(xen_callfunc_irq, cpu) = rc;
 
         debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
         rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt,
@@ -122,7 +122,7 @@ static int xen_smp_intr_init(unsigned int cpu)
                                      debug_name, NULL);
         if (rc < 0)
                 goto fail;
-        per_cpu(debug_irq, cpu) = rc;
+        per_cpu(xen_debug_irq, cpu) = rc;
 
         callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
         rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
@@ -133,19 +133,20 @@ static int xen_smp_intr_init(unsigned int cpu)
                                     NULL);
         if (rc < 0)
                 goto fail;
-        per_cpu(callfuncsingle_irq, cpu) = rc;
+        per_cpu(xen_callfuncsingle_irq, cpu) = rc;
 
         return 0;
 
  fail:
-        if (per_cpu(resched_irq, cpu) >= 0)
-                unbind_from_irqhandler(per_cpu(resched_irq, cpu), NULL);
-        if (per_cpu(callfunc_irq, cpu) >= 0)
-                unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL);
-        if (per_cpu(debug_irq, cpu) >= 0)
-                unbind_from_irqhandler(per_cpu(debug_irq, cpu), NULL);
-        if (per_cpu(callfuncsingle_irq, cpu) >= 0)
-                unbind_from_irqhandler(per_cpu(callfuncsingle_irq, cpu), NULL);
+        if (per_cpu(xen_resched_irq, cpu) >= 0)
+                unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
+        if (per_cpu(xen_callfunc_irq, cpu) >= 0)
+                unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
+        if (per_cpu(xen_debug_irq, cpu) >= 0)
+                unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
+        if (per_cpu(xen_callfuncsingle_irq, cpu) >= 0)
+                unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu),
+                                       NULL);
 
         return rc;
 }
@@ -349,10 +350,10 @@ static void xen_cpu_die(unsigned int cpu)
                 current->state = TASK_UNINTERRUPTIBLE;
                 schedule_timeout(HZ/10);
         }
-        unbind_from_irqhandler(per_cpu(resched_irq, cpu), NULL);
-        unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL);
-        unbind_from_irqhandler(per_cpu(debug_irq, cpu), NULL);
-        unbind_from_irqhandler(per_cpu(callfuncsingle_irq, cpu), NULL);
+        unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
+        unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
+        unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
+        unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
         xen_uninit_lock_cpu(cpu);
         xen_teardown_timer(cpu);
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 9d1f853120d8..0d3f07cd1b5f 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -31,14 +31,14 @@
 #define NS_PER_TICK     (1000000000LL / HZ)
 
 /* runstate info updated by Xen */
-static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate);
+static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
 
 /* snapshots of runstate info */
-static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate_snapshot);
+static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot);
 
 /* unused ns of stolen and blocked time */
-static DEFINE_PER_CPU(u64, residual_stolen);
-static DEFINE_PER_CPU(u64, residual_blocked);
+static DEFINE_PER_CPU(u64, xen_residual_stolen);
+static DEFINE_PER_CPU(u64, xen_residual_blocked);
 
 /* return an consistent snapshot of 64-bit time/counter value */
 static u64 get64(const u64 *p)
@@ -79,7 +79,7 @@ static void get_runstate_snapshot(struct vcpu_runstate_info *res)
 
         BUG_ON(preemptible());
 
-        state = &__get_cpu_var(runstate);
+        state = &__get_cpu_var(xen_runstate);
 
         /*
          * The runstate info is always updated by the hypervisor on
@@ -97,14 +97,14 @@ static void get_runstate_snapshot(struct vcpu_runstate_info *res)
 /* return true when a vcpu could run but has no real cpu to run on */
 bool xen_vcpu_stolen(int vcpu)
 {
-        return per_cpu(runstate, vcpu).state == RUNSTATE_runnable;
+        return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable;
 }
 
 void xen_setup_runstate_info(int cpu)
 {
         struct vcpu_register_runstate_memory_area area;
 
-        area.addr.v = &per_cpu(runstate, cpu);
+        area.addr.v = &per_cpu(xen_runstate, cpu);
 
         if (HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area,
                                cpu, &area))
@@ -122,7 +122,7 @@ static void do_stolen_accounting(void)
 
         WARN_ON(state.state != RUNSTATE_running);
 
-        snap = &__get_cpu_var(runstate_snapshot);
+        snap = &__get_cpu_var(xen_runstate_snapshot);
 
         /* work out how much time the VCPU has not been runn*ing*  */
         blocked = state.time[RUNSTATE_blocked] - snap->time[RUNSTATE_blocked];
@@ -133,24 +133,24 @@ static void do_stolen_accounting(void)
 
         /* Add the appropriate number of ticks of stolen time,
            including any left-overs from last time. */
-        stolen = runnable + offline + __get_cpu_var(residual_stolen);
+        stolen = runnable + offline + __get_cpu_var(xen_residual_stolen);
 
         if (stolen < 0)
                 stolen = 0;
 
         ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen);
-        __get_cpu_var(residual_stolen) = stolen;
+        __get_cpu_var(xen_residual_stolen) = stolen;
         account_steal_ticks(ticks);
 
         /* Add the appropriate number of ticks of blocked time,
            including any left-overs from last time. */
-        blocked += __get_cpu_var(residual_blocked);
+        blocked += __get_cpu_var(xen_residual_blocked);
 
         if (blocked < 0)
                 blocked = 0;
 
         ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked);
-        __get_cpu_var(residual_blocked) = blocked;
+        __get_cpu_var(xen_residual_blocked) = blocked;
         account_idle_ticks(ticks);
 }